linux_dsm_epyc7002/tools/perf/util/stat.c

423 lines
9.6 KiB
C
Raw Normal View History

#include <inttypes.h>
#include <math.h>
#include "stat.h"
#include "evlist.h"
#include "evsel.h"
#include "thread_map.h"
void update_stats(struct stats *stats, u64 val)
{
double delta;
stats->n++;
delta = val - stats->mean;
stats->mean += delta / stats->n;
stats->M2 += delta*(val - stats->mean);
if (val > stats->max)
stats->max = val;
if (val < stats->min)
stats->min = val;
}
double avg_stats(struct stats *stats)
{
return stats->mean;
}
/*
* http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
*
* (\Sum n_i^2) - ((\Sum n_i)^2)/n
* s^2 = -------------------------------
* n - 1
*
* http://en.wikipedia.org/wiki/Stddev
*
* The std dev of the mean is related to the std dev by:
*
* s
* s_mean = -------
* sqrt(n)
*
*/
double stddev_stats(struct stats *stats)
{
double variance, variance_mean;
if (stats->n < 2)
return 0.0;
variance = stats->M2 / (stats->n - 1);
variance_mean = variance / stats->n;
return sqrt(variance_mean);
}
double rel_stddev_stats(double stddev, double avg)
{
double pct = 0.0;
if (avg)
pct = 100.0 * stddev/avg;
return pct;
}
bool __perf_evsel_stat__is(struct perf_evsel *evsel,
enum perf_stat_evsel_id id)
{
struct perf_stat_evsel *ps = evsel->priv;
return ps->id == id;
}
#define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name
static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
ID(NONE, x),
ID(CYCLES_IN_TX, cpu/cycles-t/),
ID(TRANSACTION_START, cpu/tx-start/),
ID(ELISION_START, cpu/el-start/),
ID(CYCLES_IN_TX_CP, cpu/cycles-ct/),
ID(TOPDOWN_TOTAL_SLOTS, topdown-total-slots),
ID(TOPDOWN_SLOTS_ISSUED, topdown-slots-issued),
ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
};
#undef ID
void perf_stat_evsel_id_init(struct perf_evsel *evsel)
{
struct perf_stat_evsel *ps = evsel->priv;
int i;
/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) {
if (!strcmp(perf_evsel__name(evsel), id_str[i])) {
ps->id = i;
break;
}
}
}
static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
{
int i;
struct perf_stat_evsel *ps = evsel->priv;
for (i = 0; i < 3; i++)
init_stats(&ps->res_stats[i]);
perf_stat_evsel_id_init(evsel);
}
static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
{
evsel->priv = zalloc(sizeof(struct perf_stat_evsel));
if (evsel->priv == NULL)
return -ENOMEM;
perf_evsel__reset_stat_priv(evsel);
return 0;
}
static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
{
zfree(&evsel->priv);
}
static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
int ncpus, int nthreads)
{
struct perf_counts *counts;
counts = perf_counts__new(ncpus, nthreads);
if (counts)
evsel->prev_raw_counts = counts;
return counts ? 0 : -ENOMEM;
}
static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
{
perf_counts__delete(evsel->prev_raw_counts);
evsel->prev_raw_counts = NULL;
}
static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
{
int ncpus = perf_evsel__nr_cpus(evsel);
int nthreads = thread_map__nr(evsel->threads);
if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
(alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
return -ENOMEM;
return 0;
}
int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
{
struct perf_evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
if (perf_evsel__alloc_stats(evsel, alloc_raw))
goto out_free;
}
return 0;
out_free:
perf_evlist__free_stats(evlist);
return -1;
}
void perf_evlist__free_stats(struct perf_evlist *evlist)
{
struct perf_evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
perf_evsel__free_stat_priv(evsel);
perf_evsel__free_counts(evsel);
perf_evsel__free_prev_raw_counts(evsel);
}
}
void perf_evlist__reset_stats(struct perf_evlist *evlist)
{
struct perf_evsel *evsel;
evlist__for_each_entry(evlist, evsel) {
perf_evsel__reset_stat_priv(evsel);
perf_evsel__reset_counts(evsel);
}
}
static void zero_per_pkg(struct perf_evsel *counter)
{
if (counter->per_pkg_mask)
memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
}
static int check_per_pkg(struct perf_evsel *counter,
struct perf_counts_values *vals, int cpu, bool *skip)
{
unsigned long *mask = counter->per_pkg_mask;
struct cpu_map *cpus = perf_evsel__cpus(counter);
int s;
*skip = false;
if (!counter->per_pkg)
return 0;
if (cpu_map__empty(cpus))
return 0;
if (!mask) {
mask = zalloc(MAX_NR_CPUS);
if (!mask)
return -ENOMEM;
counter->per_pkg_mask = mask;
}
/*
* we do not consider an event that has not run as a good
* instance to mark a package as used (skip=1). Otherwise
* we may run into a situation where the first CPU in a package
* is not running anything, yet the second is, and this function
* would mark the package as used after the first CPU and would
* not read the values from the second CPU.
*/
if (!(vals->run && vals->ena))
return 0;
s = cpu_map__get_socket(cpus, cpu, NULL);
if (s < 0)
return -1;
*skip = test_and_set_bit(s, mask) == 1;
return 0;
}
static int
process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel,
int cpu, int thread,
struct perf_counts_values *count)
{
struct perf_counts_values *aggr = &evsel->counts->aggr;
static struct perf_counts_values zero;
bool skip = false;
if (check_per_pkg(evsel, count, cpu, &skip)) {
pr_err("failed to read per-pkg counter\n");
return -1;
}
if (skip)
count = &zero;
switch (config->aggr_mode) {
case AGGR_THREAD:
case AGGR_CORE:
case AGGR_SOCKET:
case AGGR_NONE:
if (!evsel->snapshot)
perf_evsel__compute_deltas(evsel, cpu, thread, count);
perf_counts_values__scale(count, config->scale, NULL);
if (config->aggr_mode == AGGR_NONE)
perf_stat__update_shadow_stats(evsel, count->values, cpu);
break;
case AGGR_GLOBAL:
aggr->val += count->val;
if (config->scale) {
aggr->ena += count->ena;
aggr->run += count->run;
}
case AGGR_UNSET:
default:
break;
}
return 0;
}
static int process_counter_maps(struct perf_stat_config *config,
struct perf_evsel *counter)
{
int nthreads = thread_map__nr(counter->threads);
int ncpus = perf_evsel__nr_cpus(counter);
int cpu, thread;
if (counter->system_wide)
nthreads = 1;
for (thread = 0; thread < nthreads; thread++) {
for (cpu = 0; cpu < ncpus; cpu++) {
if (process_counter_values(config, counter, cpu, thread,
perf_counts(counter->counts, cpu, thread)))
return -1;
}
}
return 0;
}
int perf_stat_process_counter(struct perf_stat_config *config,
struct perf_evsel *counter)
{
struct perf_counts_values *aggr = &counter->counts->aggr;
struct perf_stat_evsel *ps = counter->priv;
u64 *count = counter->counts->aggr.values;
u64 val;
int i, ret;
aggr->val = aggr->ena = aggr->run = 0;
perf stat: Fix interval output values We broke interval data displays with commit: 3f416f22d1e2 ("perf stat: Do not clean event's private stats") This commit removed stats cleaning, which is important for '-r' option to carry counters data over the whole run. But it's necessary to clean it for interval mode, otherwise the displayed value is avg of all previous values. Before: $ perf stat -e cycles -a -I 1000 record # time counts unit events 1.000240796 75,216,287 cycles 2.000512791 107,823,524 cycles $ perf stat report # time counts unit events 1.000240796 75,216,287 cycles 2.000512791 91,519,906 cycles Now: $ perf stat report # time counts unit events 1.000240796 75,216,287 cycles 2.000512791 107,823,524 cycles Notice the second value being bigger (91,.. < 107,..). This could be easily verified by using perf script which displays raw stat data: $ perf script CPU THREAD VAL ENA RUN TIME EVENT 0 -1 23855779 1000209530 1000209530 1000240796 cycles 1 -1 33340397 1000224964 1000224964 1000240796 cycles 2 -1 15835415 1000226695 1000226695 1000240796 cycles 3 -1 2184696 1000228245 1000228245 1000240796 cycles 0 -1 97014312 2000514533 2000514533 2000512791 cycles 1 -1 46121497 2000543795 2000543795 2000512791 cycles 2 -1 32269530 2000543566 2000543566 2000512791 cycles 3 -1 7634472 2000544108 2000544108 2000512791 cycles The sum of the first 4 values is the first interval aggregated value: 23855779 + 33340397 + 15835415 + 2184696 = 75,216,287 The sum of the second 4 values minus first value is the second interval aggregated value: 97014312 + 46121497 + 32269530 + 7634472 - 75216287 = 107,823,524 Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1454485436-20639-1-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-03 14:43:56 +07:00
/*
* We calculate counter's data every interval,
* and the display code shows ps->res_stats
* avg value. We need to zero the stats for
* interval mode, otherwise overall avg running
* averages will be shown for each interval.
*/
if (config->interval)
init_stats(ps->res_stats);
if (counter->per_pkg)
zero_per_pkg(counter);
ret = process_counter_maps(config, counter);
if (ret)
return ret;
if (config->aggr_mode != AGGR_GLOBAL)
return 0;
if (!counter->snapshot)
perf_evsel__compute_deltas(counter, -1, -1, aggr);
perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled);
for (i = 0; i < 3; i++)
update_stats(&ps->res_stats[i], count[i]);
if (verbose > 0) {
fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
perf_evsel__name(counter), count[0], count[1], count[2]);
}
/*
* Save the full runtime - to allow normalization during printout:
*/
val = counter->scale * *count;
perf_stat__update_shadow_stats(counter, &val, 0);
return 0;
}
int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_session *session)
{
struct perf_counts_values count;
struct stat_event *st = &event->stat;
struct perf_evsel *counter;
count.val = st->val;
count.ena = st->ena;
count.run = st->run;
counter = perf_evlist__id2evsel(session->evlist, st->id);
if (!counter) {
pr_err("Failed to resolve counter for stat event.\n");
return -EINVAL;
}
*perf_counts(counter->counts, st->cpu, st->thread) = count;
counter->supported = true;
return 0;
}
size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp)
{
struct stat_event *st = (struct stat_event *) event;
size_t ret;
ret = fprintf(fp, "\n... id %" PRIu64 ", cpu %d, thread %d\n",
st->id, st->cpu, st->thread);
ret += fprintf(fp, "... value %" PRIu64 ", enabled %" PRIu64 ", running %" PRIu64 "\n",
st->val, st->ena, st->run);
return ret;
}
size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp)
{
struct stat_round_event *rd = (struct stat_round_event *)event;
size_t ret;
ret = fprintf(fp, "\n... time %" PRIu64 ", type %s\n", rd->time,
rd->type == PERF_STAT_ROUND_TYPE__FINAL ? "FINAL" : "INTERVAL");
return ret;
}
size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
{
struct perf_stat_config sc;
size_t ret;
perf_event__read_stat_config(&sc, &event->stat_config);
ret = fprintf(fp, "\n");
ret += fprintf(fp, "... aggr_mode %d\n", sc.aggr_mode);
ret += fprintf(fp, "... scale %d\n", sc.scale);
ret += fprintf(fp, "... interval %u\n", sc.interval);
return ret;
}